AutoML语言实体提取score_threshold不接受为参数

Question

环境细节

• 操作系统类型和版本: Windows 10，WSL 2，Ubuntu 16.04
• Python版本: 3.7.5
• 和平执行方案版本: 19.3.1
• google-cloud-automl版本: 2.2.0

复制步骤

1. 调用以AutoML为参数的score_threshold语言实体提取

代码示例

options = ClientOptions(api_endpoint='automl.googleapis.com')
prediction_client = automl_v1.PredictionServiceClient(client_options=options)
payload = {'text_snippet': {'content': 'sample text', 'mime_type': 'text/plain'} }
params = {"score_threshold": "0.04"}
request = prediction_client.predict(name=model_name, payload=payload, params=params)

堆栈跟踪

Traceback (most recent call last):
  File "/mnt/d/alexa/lib/python3.7/site-packages/google/api_core/grpc_helpers.py", line 57, in error_remapped_callable
    return callable_(*args, **kwargs)
  File "/mnt/d/alexa/lib/python3.7/site-packages/grpc/_channel.py", line 923, in __call__
    return _end_unary_response_blocking(state, call, False, None)
  File "/mnt/d/alexa/lib/python3.7/site-packages/grpc/_channel.py", line 826, in _end_unary_response_blocking
    raise _InactiveRpcError(state)
grpc._channel._InactiveRpcError: <_InactiveRpcError of RPC that terminated with:
        status = StatusCode.INVALID_ARGUMENT
        details = "List of found errors:        1.Field: params; Message: Key `score_threshold` is not supported.      "
        debug_error_string = "{"created":"@1615914477.923586200","description":"Error received from peer ipv4:172.217.4.74:***","file":"src/core/lib/surface/call.cc","file_line":1061,"grpc_message":"List of found errors:\t1.Field: params; Message: Key `score_threshold` is not supported.\t","grpc_status":3}"
>

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "google_keyword_generation.py", line 167, in <module>
    call_nlp()
  File "google_keyword_generation.py", line 137, in call_nlp
    request = prediction_client.predict(name=model_name, payload=payload, params=params)
  File "/mnt/d/alexa/lib/python3.7/site-packages/google/cloud/automl_v1/services/prediction_service/client.py", line 498, in predict
    response = rpc(request, retry=retry, timeout=timeout, metadata=metadata,)
  File "/mnt/d/alexa/lib/python3.7/site-packages/google/api_core/gapic_v1/method.py", line 145, in __call__
    return wrapped_func(*args, **kwargs)
  File "/mnt/d/alexa/lib/python3.7/site-packages/google/api_core/grpc_helpers.py", line 59, in error_remapped_callable
    six.raise_from(exceptions.from_grpc_error(exc), exc)
  File "<string>", line 3, in raise_from
google.api_core.exceptions.InvalidArgument: 400 List of found errors:   1.Field: params; Message: Key `score_threshold` is not supported.

Answer 1

参数params -> score_threshold是，不能用于AutoML NL实体提取。这仅适用于AutoML视觉分类和AutoML视觉对象检测。见用于预测()的python引用。

(Sequence~.prediction_service.PredictRequest.ParamsEntry) params - 附加特定于域的参数，任何字符串都必须长达25000个字符. AutoML视觉分类 score_threshold：(浮点)从0.0到1.0的值。当模型对图像进行预测时，它只会产生至少具有这个可信度的结果。缺省值为0.5。 AutoML视觉目标检测 score_threshold：(浮点)当模型检测到图像上的对象时，它只会产生至少有这个置信度的边界框。值在0到1范围内，默认值为0.5。 max_bounding_box_count：(int64)返回的边框的最大数量。缺省值为100。服务器可能会限制返回的边界框的数量。

但是，如果使用的是AutoML NL分类，则可以使用预测()设置score_threshold。